API

Provides HTTP API tools (GET, POST, PUT, DELETE) to fetch, send, update, and delete data from web APIs.

typescript

2

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "fikri2992-mcp0": {
      "command": "npx",
      "args": [
        "mcp-api-server"
      ],
      "env": {
        "DEBUG": "true",
        "USER_AGENT": "MyApp/1.0.0",
        "API_TIMEOUT": "60000",
        "ALLOW_LOCALHOST": "true",
        "ALLOW_PRIVATE_IPS": "false",
        "MAX_RESPONSE_LENGTH": "100000"
      }
    }
  }
}

You can generate and run a dedicated MCP server that exposes HTTP API tools for your AI assistant. This server lets you perform GET, POST, PUT, and DELETE requests to any web API, with configurable safety, logging, and request handling to fit development and production needs.

How to use

You run the MCP API server locally and connect your MCP client to it. Start the server with a simple command, then use the available tools from your AI assistant to fetch data, send data, update resources, or remove items from remote APIs. The server validates requests, applies security rules, and logs activity for debugging.

How to install

Prerequisites: you need Node.js and npm installed on your system.

# Install the MCP Builder CLI globally for easy access to the tools
npm install -g mcp-builder

# Start the API server directly (no installation required if using NPX)
npx mcp-api-server

# Or start with debugging and localhost access enabled for development
npx mcp-api-server --debug --allow-localhost

# You can also run the server via Node if you prefer a local build
node dist/src/index.js
node dist/src/index.js --debug --allow-localhost

Configuration and security

Configure how the server handles requests and what it exposes. The server includes options to enable debug logging, allow localhost requests for development, and permit private IP access in trusted environments. It also enforces request timeouts and limits the maximum response size to protect resources.

# Example environment variables
API_TIMEOUT=60000          # Request timeout in milliseconds
ALLOW_LOCALHOST=true      # Allow requests to localhost (127.0.0.1)
ALLOW_PRIVATE_IPS=false   # Do not allow requests to private IP ranges by default
MAX_RESPONSE_LENGTH=100000 # Maximum response length in bytes
USER_AGENT="MyApp/1.0.0"   # Custom user agent string for requests
DEBUG=true                # Enable detailed logging

Tools and how to use them

The server provides a set of MCP tools that your AI assistant can invoke to perform HTTP requests against remote APIs.

Available tools

api_get

Make an HTTP GET request to retrieve data from a URL. Include optional headers to customize the request.

api_post

Make an HTTP POST request to send data to a URL. Include body and headers as needed.

api_put

Make an HTTP PUT request to update data at a URL. Include body and headers as needed.

api_delete

Make an HTTP DELETE request to remove data at a URL. Include headers as needed.